Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 746 745 507 813 592 278 534 558  52  51 699 701 288 754 846 609 904 484 945 526
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 526 507 904  NA  52 846 558 813 945 746 278 534 484 288 745  51  NA 592 699 754 701 609  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 3 2 4 4 1 1 4 4 3
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "d" "z" "g" "t" "f" "N" "K" "Q" "V" "D"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 17 19
which( manyNumbersWithNA > 900 )
[1] 3 9
which( is.na( manyNumbersWithNA ) )
[1]  4 17 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 904 945
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 904 945
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 904 945

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "N" "K" "Q" "V" "D"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "d" "z" "g" "t" "f"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  3  5  7  8 18 20
sum( manyNumbers %in% 300:600 )
[1] 6

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "large" "large" NA      "small" "large" "large" "large" "large" "large" "small" "large" "small" "small" "large" "small" NA      "large" "large" "large"
[21] "large" "large" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "large"   "large"   "UNKNOWN" "small"   "large"   "large"   "large"   "large"   "large"   "small"   "large"   "small"   "small"   "large"   "small"  
[17] "UNKNOWN" "large"   "large"   "large"   "large"   "large"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 526 507 904  NA   0 846 558 813 945 746   0 534   0   0 745   0  NA 592 699 754 701 609  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 3 2 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  3  2  4
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 9
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 945
which.min( manyNumbersWithNA )
[1] 16
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 51
range( manyNumbersWithNA, na.rm = TRUE )
[1]  51 945

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 526 507 904  NA  52 846 558 813 945 746 278 534 484 288 745  51  NA 592 699 754 701 609  NA
sort( manyNumbersWithNA )
 [1]  51  52 278 288 484 507 526 534 558 592 609 699 701 745 746 754 813 846 904 945
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  51  52 278 288 484 507 526 534 558 592 609 699 701 745 746 754 813 846 904 945  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 945 904 846 813 754 746 745 701 699 609 592 558 534 526 507 484 288 278  52  51  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 526 507 904  NA  52
order( manyNumbersWithNA[1:5] )
[1] 5 2 1 3 4
rank( manyNumbersWithNA[1:5] )
[1] 3 2 4 5 1
sort( mixedLetters )
 [1] "d" "D" "f" "g" "K" "N" "Q" "t" "V" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 6.5 3.0 9.0 6.5 3.0 3.0 9.0 3.0 9.0 3.0
rank( manyDuplicates, ties.method = "min" )
 [1] 6 1 8 6 1 1 8 1 8 1
rank( manyDuplicates, ties.method = "random" )
 [1]  7  1  8  6  2  3  9  5 10  4

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -1.10228814 -0.98725768 -0.14996734  1.11902339 -0.03119318  0.91440077 -0.50491786  1.78671117
[14] -0.35495474 -0.24869741
round( v, 0 )
 [1] -1  0  0  0  1 -1 -1  0  1  0  1 -1  2  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -1.1 -1.0 -0.1  1.1  0.0  0.9 -0.5  1.8 -0.4 -0.2
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -1.10 -0.99 -0.15  1.12 -0.03  0.91 -0.50  1.79 -0.35 -0.25
floor( v )
 [1] -1 -1  0  0  1 -2 -1 -1  1 -1  0 -1  1 -1 -1
ceiling( v )
 [1] -1  0  0  1  1 -1  0  0  2  0  1  0  2  0  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC